© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10661
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions and their structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing braces and parentheses in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.69
    Tembelea
    -0.67
    IntoConstraints
    -0.66
    ConstraintMaker
    -0.57
    IndentedString
    -0.54
    Personendaten
    -0.53
    CodeAttribute
    -0.53
    DIPSETTING
    -0.52
    цездатний
    -0.52
    HasForeignKey
    -0.50
    POSITIVE LOGITS
    function
    1.13
     function
    1.11
     Function
    0.68
     funktion
    0.65
     window
    0.62
     Funktion
    0.61
    window
    0.60
     fonction
    0.59
    funktion
    0.57
     functions
    0.56
    Activations Density 0.170%

    No Known Activations